Ptally Engineering
The team behind the Ptally rating engine, API and MCP server. They write about model formats, testing, performance and how AI agents work with pricing models.
Articles
4Why insurance pricing models should be human readable, especially when AI writes them
As AI drafts more insurance pricing logic, the format of the model becomes a control. This article explains why declarative, readable pricing models are faster to review and audit than generated code.
Every rate change needs a test suite: regression testing for insurance pricing
How to regression test insurance pricing models: building test cases from worked examples, covering declines and referrals, and checking every rate change before release.
Using Claude and ChatGPT to build insurance pricing models: what works and what doesn't
A practical guide to building and editing insurance pricing models with AI clients such as Claude and ChatGPT over MCP: where they help, where they struggle, and how to keep people in control.
Replacing a spreadsheet rater: when to move and how to do it safely
Signs that an Excel rating model has reached its limits, the risks of keeping it, and a step-by-step migration that uses the spreadsheet's own results as tests.
Other authors
See your product as a live model
Send us your rating guide. We'll come back with a working, tested model. There is no implementation fee.